phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

more msg

Browse source
This commit is contained in:
Xi Yan 2024-12-02 16:14:04 -08:00
parent 0e718b9712
commit 06b9566eb6
1 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/distribution/ui/page/evaluations/native_eval.py
View file

@ -145,6 +145,13 @@ def native_evaluation_page():
st.write("(Optional) Define scoring function parameters here") st.write("(Optional) Define scoring function parameters here")
with run_tab: with run_tab:
# Add info box to explain configurations being used
st.info(
"""
Review the configurations that will be used for this evaluation run, make any necessary changes, and then click the "Run Evaluation" button.
"""
)
dataset_id = eval_tasks[selected_eval_task].dataset_id dataset_id = eval_tasks[selected_eval_task].dataset_id
rows = llama_stack_api.client.datasetio.get_rows_paginated( rows = llama_stack_api.client.datasetio.get_rows_paginated(
dataset_id=dataset_id, dataset_id=dataset_id,
@ -165,11 +172,18 @@ def native_evaluation_page():
"eval_candidate": eval_candidate, "eval_candidate": eval_candidate,
"scoring_params": {}, "scoring_params": {},
} }
st.markdown("##### Evaluation Task")
st.write("Go back to (1) Select Eval Task to make changes to the eval task. ")
st.json(eval_tasks[selected_eval_task], expanded=True) st.json(eval_tasks[selected_eval_task], expanded=True)
st.markdown("##### Evaluation Task Configuration")
st.write(
"Go back to (2) Define Eval Candidate and (3) Define Scoring Parameters to make changes to the configuration. "
)
st.json(eval_task_config, expanded=True) st.json(eval_task_config, expanded=True)
# Add run button and handle evaluation # Add run button and handle evaluation
if st.button("Run Evaluation"): if st.button("Run Evaluation"):
progress_text = "Running evaluation..." progress_text = "Running evaluation..."
progress_bar = st.progress(0, text=progress_text) progress_bar = st.progress(0, text=progress_text)
rows = rows.rows rows = rows.rows